[PATCH V2 1/3] MIPS: Crash kernel should be able to see old memories

[PATCH V2 1/3] MIPS: Crash kernel should be able to see old memories

[Huacai Chen]

Kexec-tools use mem=X@Y to pass usable memories to crash kernel, but in
commit a94e4f24ec836c8984f83959 ("MIPS: init: Drop boot_mem_map") all
BIOS passed memories are removed by early_parse_mem(). I think this is
reasonable for a normal kernel but not for a crash kernel, because a
crash kernel should be able to see all old memories, even though it is
not supposed to use them.

Fixes: a94e4f24ec836c8984f83959 ("MIPS: init: Drop boot_mem_map")
Signed-off-by: Huacai Chen <chenhc@lemote.com>
---
 arch/mips/kernel/setup.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c
index 4c04a86..e2804a2 100644
--- a/arch/mips/kernel/setup.c
+++ b/arch/mips/kernel/setup.c
@@ -392,8 +392,10 @@ static int __init early_parse_mem(char *p)
 	 */
 	if (usermem == 0) {
 		usermem = 1;
+#ifndef CONFIG_CRASH_DUMP
 		memblock_remove(memblock_start_of_DRAM(),
 			memblock_end_of_DRAM() - memblock_start_of_DRAM());
+#endif
 	}
 	start = 0;
 	size = memparse(p, &p);
-- 
2.7.0

[PATCH V2 2/3] MIPS: Reserve extra memory for crash dump

[Huacai Chen]

Traditionally, MIPS's contiguous low memory can be as less as 256M, so
crashkernel=X@Y may be unable to large enough in some cases. Moreover,
for the "multi numa node + sparse memory model" case, it is attempt to
allocate section_mem_maps on every node. Thus, if the total memory of a
node is more than 1GB, we reserve the top 128MB for the crash kernel.

Signed-off-by: Huacai Chen <chenhc@lemote.com>
---
 arch/mips/kernel/setup.c | 63 ++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 63 insertions(+)

diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c
index e2804a2..90d4a2e 100644
--- a/arch/mips/kernel/setup.c
+++ b/arch/mips/kernel/setup.c
@@ -29,6 +29,7 @@
 #include <linux/of_fdt.h>
 #include <linux/of_reserved_mem.h>
 #include <linux/dmi.h>
+#include <linux/crash_dump.h>
 
 #include <asm/addrspace.h>
 #include <asm/bootinfo.h>
@@ -55,6 +56,10 @@ EXPORT_SYMBOL(cpu_data);
 struct screen_info screen_info;
 #endif
 
+#ifdef CONFIG_CRASH_DUMP
+static phys_addr_t crashmem_start, crashmem_size;
+#endif
+
 /*
  * Setup information
  *
@@ -404,6 +409,13 @@ static int __init early_parse_mem(char *p)
 
 	add_memory_region(start, size, BOOT_MEM_RAM);
 
+#ifdef CONFIG_CRASH_DUMP
+	if (start && size) {
+		crashmem_start = start;
+		crashmem_size = size;
+	}
+#endif
+
 	return 0;
 }
 early_param("mem", early_parse_mem);
@@ -642,6 +654,48 @@ static void __init bootcmdline_init(void)
 		bootcmdline_append(builtin_cmdline, COMMAND_LINE_SIZE);
 }
 
+/* Traditionally, MIPS's contiguous low memory is 256M, so crashkernel=X@Y is
+ * unable to be large enough in some cases. Thus, if the total memory of a node
+ * is more than 1GB, we reserve the top 128MB for the crash kernel */
+static void reserve_crashm_region(int node, unsigned long s0, unsigned long e0)
+{
+#ifdef CONFIG_KEXEC
+	if (crashk_res.start == crashk_res.end)
+		return;
+
+	if ((e0 - s0) <= (SZ_1G >> PAGE_SHIFT))
+		return;
+
+	s0 = e0 - (SZ_128M >> PAGE_SHIFT);
+
+	memblock_reserve(PFN_PHYS(s0), (e0 - s0) << PAGE_SHIFT);
+#endif
+}
+
+static void reserve_oldmem_region(int node, unsigned long s0, unsigned long e0)
+{
+#ifdef CONFIG_CRASH_DUMP
+	unsigned long s1, e1;
+
+	if (!is_kdump_kernel())
+		return;
+
+	if ((e0 - s0) > (SZ_1G >> PAGE_SHIFT))
+		e0 = e0 - (SZ_128M >> PAGE_SHIFT);
+
+	/* crashmem_start is crashk_res reserved by primary kernel */
+	s1 = PFN_UP(crashmem_start);
+	e1 = PFN_DOWN(crashmem_start + crashmem_size);
+
+	if (node == 0) {
+		memblock_reserve(PFN_PHYS(s0), (s1 - s0) << PAGE_SHIFT);
+		memblock_reserve(PFN_PHYS(e1), (e0 - e1) << PAGE_SHIFT);
+	} else {
+		memblock_reserve(PFN_PHYS(s0), (e0 - s0) << PAGE_SHIFT);
+	}
+#endif
+}
+
 /*
  * arch_mem_init - initialize memory management subsystem
  *
@@ -666,6 +720,9 @@ static void __init bootcmdline_init(void)
  */
 static void __init arch_mem_init(char **cmdline_p)
 {
+	unsigned int node;
+	unsigned long start_pfn, end_pfn;
+
 	/* call board setup routine */
 	plat_mem_setup();
 	memblock_set_bottom_up(true);
@@ -711,6 +768,12 @@ static void __init arch_mem_init(char **cmdline_p)
 	if (crashk_res.start != crashk_res.end)
 		memblock_reserve(crashk_res.start, resource_size(&crashk_res));
 #endif
+	for_each_online_node(node) {
+		get_pfn_range_for_nid(node, &start_pfn, &end_pfn);
+		reserve_crashm_region(node, start_pfn, end_pfn);
+		reserve_oldmem_region(node, start_pfn, end_pfn);
+	}
+
 	device_tree_init();
 
 	/*
-- 
2.7.0

[PATCH V2 3/3] MIPS: Loongson64: Add kexec/kdump support

[Huacai Chen]

Add kexec/kdump support for Loongson64 by:
1, Provide Loongson-specific kexec functions: loongson_kexec_prepare(),
   loongson_kexec_shutdown() and loongson_crash_shutdown();
2, Provide Loongson-specific assembly code in kexec_smp_wait();

To start Loongson64, The boot CPU needs 3 parameters:
fw_arg0: the number of arguments in cmdline (i.e., argc).
fw_arg1: structure holds cmdline such as "root=/dev/sda1 console=tty"
         (i.e., argv).
fw_arg2: environment (i.e., envp, additional boot parameters from LEFI).

Non-boot CPUs do not need one parameter as the IPI mailbox base address.
They query their own IPI mailbox to get PC, SP and GP in a loopi, until
the boot CPU brings them up.

loongson_kexec_prepare(): Setup cmdline for kexec/kdump. The kexec/kdump
cmdline comes from kexec's "append" option string. This structure will
be parsed in fw_init_cmdline() of arch/mips/fw/lib/cmdline.c. Both image
->control_code_page and the cmdline need to be in a safe memory region
(memory allocated by the old kernel may be corrupted by the new kernel).
In order to maintain compatibility for the old firmware, the low 2MB is
reserverd and safe for Loongson. So let KEXEC_CTRL_CODE and KEXEC_ARGV_
ADDR be here. LEFI parameters may be corrupted at runtime, so backup it
at mips_reboot_setup(), and then restore it at loongson_kexec_shutdown()
/loongson_crash_shutdown().

loongson_kexec_shutdown(): Wake up all present CPUs and let them go to
reboot_code_buffer. Pass the kexec parameters to kexec_args.

loongson_crash_shutdown(): Pass the kdump parameters to kexec_args.

The assembly part in kexec_smp_wait provide a routine as BIOS does, in
order to keep secondary CPUs in a querying loop.

The layout of low 2MB memory in our design: 
0x80000000, the first MB, the first 64K, Exception vectors
0x80010000, the first MB, the second 64K, STR (suspend) data
0x80020000, the first MB, the third and fourth 64K, UEFI HOB
0x80040000, the first MB, the fifth 64K, RT-Thread for SMC
0x80100000, the second MB, the first 64K, KEXEC code
0x80108000, the second MB, the second 64K, KEXEC data

Cc: Eric Biederman <ebiederm@xmission.com>
Signed-off-by: Huacai Chen <chenhc@lemote.com>
Signed-off-by: Jinyang He <hejinyang@loongson.cn>
Signed-off-by: Youling Tang <tangyouling@loongson.cn>
---
 arch/mips/kernel/relocate_kernel.S |  27 +++++++++
 arch/mips/loongson64/reset.c       | 111 +++++++++++++++++++++++++++++++++++++
 2 files changed, 149 insertions(+)

diff --git a/arch/mips/kernel/relocate_kernel.S b/arch/mips/kernel/relocate_kernel.S
index ac87089..91b2932 100644
--- a/arch/mips/kernel/relocate_kernel.S
+++ b/arch/mips/kernel/relocate_kernel.S
@@ -6,6 +6,7 @@
 
 #include <asm/asm.h>
 #include <asm/asmmacro.h>
+#include <asm/cpu.h>
 #include <asm/regdef.h>
 #include <asm/mipsregs.h>
 #include <asm/stackframe.h>
@@ -133,6 +133,32 @@ LEAF(kexec_smp_wait)
 #else
 	sync
 #endif
+
+#ifdef CONFIG_CPU_LOONGSON64
+	/* s0:prid s1:initfn */
+	/* a0:base t1:cpuid t2:node t9:count */
+	mfc0		t1, CP0_EBASE
+	andi		t1, MIPS_EBASE_CPUNUM
+	dins		a0, t1, 8, 2       /* insert core id*/
+	dext		t2, t1, 2, 2
+	dins		a0, t2, 44, 2      /* insert node id */
+	mfc0		s0, CP0_PRID
+	andi		s0, s0, (PRID_IMP_MASK | PRID_REV_MASK)
+	beq		s0, (PRID_IMP_LOONGSON_64C | PRID_REV_LOONGSON3B_R1), 1f
+	beq		s0, (PRID_IMP_LOONGSON_64C | PRID_REV_LOONGSON3B_R2), 1f
+	b		2f                 /* Loongson-3A1000/3A2000/3A3000/3A4000 */
+1:	dins		a0, t2, 14, 2      /* Loongson-3B1000/3B1500 need bit 15~14 */
+2:	li		t9, 0x100          /* wait for init loop */
+3:	addiu		t9, -1             /* limit mailbox access */
+	bnez		t9, 3b
+	ld		s1, 0x20(a0)       /* get PC via mailbox reg0 */
+	beqz		s1, 2b
+	ld		sp, 0x28(a0)       /* get SP via mailbox reg1 */
+	ld		gp, 0x30(a0)       /* get GP via mailbox reg2 */
+	ld		a1, 0x38(a0)
+	jr		s1                 /* jump to initial PC */
+#endif
+
 	j		s1
 	END(kexec_smp_wait)
 #endif
diff --git a/arch/mips/loongson64/reset.c b/arch/mips/loongson64/reset.c
index 3bb8a1e..b1e71f37 100644
--- a/arch/mips/loongson64/reset.c
+++ b/arch/mips/loongson64/reset.c
@@ -6,9 +6,14 @@
  * Copyright (C) 2009 Lemote, Inc.
  * Author: Zhangjin Wu, wuzhangjin@gmail.com
  */
+#include <linux/cpu.h>
+#include <linux/delay.h>
 #include <linux/init.h>
+#include <linux/kexec.h>
 #include <linux/pm.h>
+#include <linux/slab.h>
 
+#include <asm/bootinfo.h>
 #include <asm/idle.h>
 #include <asm/reboot.h>
 
@@ -47,12 +52,120 @@ static void loongson_halt(void)
 	}
 }
 
+#ifdef CONFIG_KEXEC
+
+/* 0X80000000~0X80200000 is safe */
+#define MAX_ARGS	64
+#define KEXEC_CTRL_CODE	0xFFFFFFFF80100000UL
+#define KEXEC_ARGV_ADDR	0xFFFFFFFF80108000UL
+#define KEXEC_ARGV_SIZE	COMMAND_LINE_SIZE
+#define KEXEC_ENVP_SIZE	4800
+
+static int kexec_argc;
+static int kdump_argc;
+static void *kexec_argv;
+static void *kdump_argv;
+static void *kexec_envp;
+
+static int loongson_kexec_prepare(struct kimage *image)
+{
+	int i, argc = 0;
+	unsigned int *argv;
+	char *str, *ptr, *bootloader = "kexec";
+
+	/* argv at offset 0, argv[] at offset KEXEC_ARGV_SIZE/2 */
+	if (image->type == KEXEC_TYPE_DEFAULT)
+		argv = (unsigned int *)kexec_argv;
+	else
+		argv = (unsigned int *)kdump_argv;
+
+	argv[argc++] = (unsigned int)(KEXEC_ARGV_ADDR + KEXEC_ARGV_SIZE/2);
+
+	for (i = 0; i < image->nr_segments; i++) {
+		if (!strncmp(bootloader, (char *)image->segment[i].buf,
+				strlen(bootloader))) {
+			/*
+			 * convert command line string to array
+			 * of parameters (as bootloader does).
+			 */
+			int offt;
+			str = (char *)argv + KEXEC_ARGV_SIZE/2;
+			memcpy(str, image->segment[i].buf, KEXEC_ARGV_SIZE/2);
+			ptr = strchr(str, ' ');
+
+			while (ptr && (argc < MAX_ARGS)) {
+				*ptr = '\0';
+				if (ptr[1] != ' ') {
+					offt = (int)(ptr - str + 1);
+					argv[argc] = KEXEC_ARGV_ADDR + KEXEC_ARGV_SIZE/2 + offt;
+					argc++;
+				}
+				ptr = strchr(ptr + 1, ' ');
+			}
+			break;
+		}
+	}
+
+	if (image->type == KEXEC_TYPE_DEFAULT)
+		kexec_argc = argc;
+	else
+		kdump_argc = argc;
+
+	/* kexec/kdump need a safe page to save reboot_code_buffer */
+	image->control_code_page = virt_to_page((void *)KEXEC_CTRL_CODE);
+
+	return 0;
+}
+
+static void loongson_kexec_shutdown(void)
+{
+#ifdef CONFIG_SMP
+	int cpu;
+
+	/* All CPUs go to reboot_code_buffer */
+	for_each_possible_cpu(cpu)
+		if (!cpu_online(cpu))
+			cpu_device_up(get_cpu_device(cpu));
+#endif
+	kexec_args[0] = kexec_argc;
+	kexec_args[1] = fw_arg1;
+	kexec_args[2] = fw_arg2;
+	secondary_kexec_args[0] = TO_UNCAC(0x3ff01000);
+	memcpy((void *)fw_arg1, kexec_argv, KEXEC_ARGV_SIZE);
+	memcpy((void *)fw_arg2, kexec_envp, KEXEC_ENVP_SIZE);
+}
+
+static void loongson_crash_shutdown(struct pt_regs *regs)
+{
+	default_machine_crash_shutdown(regs);
+	kexec_args[0] = kdump_argc;
+	kexec_args[1] = fw_arg1;
+	kexec_args[2] = fw_arg2;
+	secondary_kexec_args[0] = TO_UNCAC(0x3ff01000);
+	memcpy((void *)fw_arg1, kdump_argv, KEXEC_ARGV_SIZE);
+	memcpy((void *)fw_arg2, kexec_envp, KEXEC_ENVP_SIZE);
+}
+
+#endif
+
 static int __init mips_reboot_setup(void)
 {
 	_machine_restart = loongson_restart;
 	_machine_halt = loongson_halt;
 	pm_power_off = loongson_poweroff;
 
+#ifdef CONFIG_KEXEC
+	kexec_argv = kmalloc(KEXEC_ARGV_SIZE, GFP_KERNEL);
+	kdump_argv = kmalloc(KEXEC_ARGV_SIZE, GFP_KERNEL);
+	kexec_envp = kmalloc(KEXEC_ENVP_SIZE, GFP_KERNEL);
+	fw_arg1 = KEXEC_ARGV_ADDR;
+	memcpy(kexec_envp, (void *)fw_arg2, KEXEC_ENVP_SIZE);
+
+	_machine_kexec_prepare = loongson_kexec_prepare;
+	_machine_kexec_shutdown = loongson_kexec_shutdown;
+	_machine_crash_shutdown = loongson_crash_shutdown;
+#endif
+
 	return 0;
 }
 
-- 
2.7.0